← Video Question Answering

Papers with Code · CC BY-SA 4.0

STAR Benchmark

아카이브 평가 17건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
VLAP (4 frames)	Average Accuracy 67.1	ViLA: Efficient Video-Language Alignment for Video Question Answering 2023-12-13	코드 1
LLaMA-VQA	Average Accuracy 65.4	Large Language Models are Temporal and Causal Reasoners for Video Question Answering 2023-10-24	코드 1
SeViLA	Average Accuracy 64.9	Self-Chained Image-Language Model for Video Localization and Question Answering 2023-05-11	코드 1
InternVideo	Average Accuracy 58.7	InternVideo: General Video Foundation Models via Generative and Discriminative Learning 2022-12-06	코드 1 · 코드 2
GF(sup)	Average Accuracy 53.94	Glance and Focus: Memory Prompting for Multi-Event Video Question Answering 2024-01-03	코드 1
GF(uns)	Average Accuracy 53.86	Glance and Focus: Memory Prompting for Multi-Event Video Question Answering 2024-01-03	코드 1
MIST	Average Accuracy 51.13	MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering 2022-12-19	코드 1
Temp[ATP]	Average Accuracy 48.37	Revisiting the "Video" in Video-Language Understanding 2022-06-03	코드 1
AnyMAL-70B (0-shot)	Average Accuracy 48.2	AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model 2023-09-27	코드 1
All-in-one	Average Accuracy 47.5	All in One: Exploring Unified Video-Language Pre-training 2022-03-14	코드 1
TraveLER (0-shot)	Average Accuracy 44.9	TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering 2024-04-01	코드 1
SeViLA (0-shot)	Average Accuracy 44.6	Self-Chained Image-Language Model for Video Localization and Question Answering 2023-05-11	코드 1
Flamingo-9B (4-shot)	Average Accuracy 42.8	Flamingo: a Visual Language Model for Few-Shot Learning 2022-04-29	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
Flamingo-80B (4-shot)	Average Accuracy 42.4	Flamingo: a Visual Language Model for Few-Shot Learning 2022-04-29	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
Flamingo-9B (0-shot)	Average Accuracy 41.8	Flamingo: a Visual Language Model for Few-Shot Learning 2022-04-29	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
Flamingo-80B (0-shot)	Average Accuracy 39.7	Flamingo: a Visual Language Model for Few-Shot Learning 2022-04-29	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
SHG-VQA (trained from scratch)	Average Accuracy 39.47	Learning Situation Hyper-Graphs for Video Question Answering 2023-04-18	코드 1